Editing & Tools

How to Edit Video with Codex: Batch-Edit a Folder of Clips

Fuxuan Guo
29 min read
How to Edit Video with Codex: Batch-Edit a Folder of Clips
Contents
  1. Can Codex edit videos, and how does Codex video editing work?
  2. What did our 3-clip Codex batch edit produce?
  3. How do you batch-edit a folder of clips in Codex in five steps?
  4. What do you need before you start?
  5. Why split a batch edit into A-Roll and B-Roll passes?
  6. How do you edit a folder of videos with Codex step by step?
  7. Which prompts can you copy for other Codex video editing jobs?
  8. What do you still need to check yourself before publishing?
  9. How do you troubleshoot Codex and ChatCut Desktop?

Yes. You can edit video with Codex on a Mac (macOS 13+) or Windows PC (Windows 10+ x64) by connecting OpenAI’s Codex agent to ChatCut Desktop, turning plain-English prompts in your terminal or desktop app into cuts, captions, titles, B-roll, and music on an editable multi-track timeline. This ChatCut Desktop workflow does not support Linux. We make ChatCut, the AI video editor used in this walkthrough.

About this walkthrough: This walkthrough records one actual batch-editing project run in Codex CLI through ChatCut Desktop. Steps 2–8 reproduce its seven recorded editing requests as text; the images are real Desktop captures or export frames, not screenshots of a Codex conversation. Other copyable prompts are suggested variations. Timings and ChatCut charges describe this project only; Codex costs were not measured.

If you only need to polish one recording inside the ChatGPT desktop app, read our single-video guide on how to edit video with ChatGPT. This tutorial covers the Codex video editing workflow for batch-editing an entire local folder of clips at once. On November 18, 2026, we pointed Codex CLI (0.169.0-alpha.11.1, running gpt-6-astra at high reasoning effort) at a folder of three 40-second horizontal talking-head takes (120.05 seconds total). Across seven prompts and about 13.5 minutes, Codex imported and transcribed all three files together, cut fillers and dead air onto three separate 9:16 timelines in one project, reused one word-level caption template, one 2-second title card template, and one auto-ducked music track across the batch, quoted and generated one 4-second B-roll clip for 2.88 ChatCut credits, and exported three 1080×1920 MP4s. Subsequent command-line stream checks, full decoding, and sampled-frame review are outside that 13.5-minute interval. The run did not benchmark other agents.

Can Codex edit videos, and how does Codex video editing work?

In OpenAI’s current ChatGPT desktop app and Codex CLI, Codex is an agent built to inspect local folders, run commands, and call connected Model Context Protocol (MCP) servers. On its own, Codex has no video timeline. Creators who search can Codex edit videos usually run into three very different setups:

SetupWhat Codex actually doesWhat you get backWhere it breaks down
Codex alone (no video tools)Reads an .srt or transcript and suggests timestamps or shell commandsEdit notes or shell scriptsA transcript alone does not provide a visual editing workspace; previews and rendered effects require additional tools
Codex + code renderers (Remotion or HyperFrames)Writes React or HTML animation code and renders a video fileA flat .mp4 plus source codeThe editable source is a code project; available preview and editing controls depend on the renderer
Codex + ChatCut DesktopImports local files, edits transcripts, builds timelines, applies reusable caption/title templates, and exportsEditable multi-track timelines inside ChatCut Desktop plus finished MP4 or XML handoff filesRequires macOS 13+ or Windows 10+ (x64) and an internet connection (Product Facts)

Connecting ChatCut for Codex gives you both halves of the job: Codex handles the repetitive folder-level work—passing file arrays, reusing one caption and title component across multiple timelines, and checking rendered outputs with command-line tools—while ChatCut Desktop keeps every cut, caption, overlay, and audio track open for manual inspection.

Where Codex runs, which model it uses, and how billing splits

  • Three local ways to run Codex with ChatCut. You can run prompts in codex in your terminal (used for folder paths and post-export ffprobe checks in this run), select Codex inside the ChatGPT desktop app, or choose Codex CLI under Agent Selection at the bottom of ChatCut Desktop’s AI panel so the chat sits beside the Viewer and Timeline. OpenAI documents shared MCP settings for its desktop app, CLI, and IDE extension in ~/.codex/config.toml (OpenAI MCP docs). Existing cloud projects in app.chatcut.io use the separate hosted Web plugin instead.
  • Your own OpenAI model and subscription. Codex model access depends on your account and sign-in method—our November 18 run used gpt-6-astra at high reasoning effort in Codex CLI, and OpenAI’s Codex models guide also documents gpt-6.2-astra and gpt-6.2-sol across the app and CLI. Check the plan and surface before starting: OpenAI currently lists Free access in the desktop app subject to rollout, and CLI access on eligible plans or with an API key (OpenAI Codex pricing).
  • Separate OpenAI and ChatCut billing. When Codex drives ChatCut Desktop, Codex’s reasoning uses its own subscription allowance or API billing rather than ChatCut’s built-in Agent meter (Credits policy). Importing local clips, speech transcription, timeline cuts, captions, agent-authored titles, stock CC0 audio, and local MP4 exports cost 0 ChatCut credits and export without a watermark on ChatCut’s Free plan (Free caps cloud exports at 60 cumulative minutes, while Desktop renders locally on your machine). You spend ChatCut credits only when you approve ChatCut-hosted AI media generation; AI video and ChatCut image generation require a paid plan starting at $25/month for 100 credits.

What did our 3-clip Codex batch edit produce?

Below is Short B (26.8 seconds, 1080×1920, 30 fps), one of the three vertical MP4s exported at the end of our seven-prompt Codex CLI session, re-encoded from the 40.80 MB master to 5.19 MB (4.95 MiB) for web playback. Both files contain 805 video frames at 30 fps; compression changes image data:

Demo
Short B from our three-clip Codex CLI batch run (26.8 seconds, 1080×1920, 30 fps, 2.88 ChatCut credits total across the entire three-video batch). Unmute to hear the CC0 ambient music bed ducking underneath the presenter's voice.

Watch what happens across those 26.8 seconds—and how the same packaging rules carried across all three clips in the folder:

  • 0:00 to 0:02: A shared 2-second black opening card (CODEX × CHATCUT / 02 above “Upload. Prompt. Edit”), built from the same template as Shorts A and C.
  • 0:02 to 0:10.9: The horizontal 1920×1080 source take reframed to 1080×1920 (with horizontal framing shifted so the off-center speaker stays centered) and styled with bold white Mulish captions that highlight only the currently spoken word in orange.
  • 0:10.9 to 0:14.9: A 4-second AI B-roll cutaway generated with Seedance 2.5 Flash (2.88 credits, quoted before submission) showing hands typing at a warm-lit laptop workspace while the speaker’s voice and word-level captions continue uninterrupted.
  • 0:00 to 0:26.8: One CC0 background music track reused across all three timelines at -6 dB with a 1-second fade-in, 1.5-second fade-out, and automatic voice ducking.

Here is how the complete three-file folder came out:

Source fileRaw 16:9 lengthTrimmed spoken cutFinal 9:16 MP4 (with 2s title)Opening title cardWhat Codex cut from the transcript
talk-codex-a.mp440.04 s28.00 s30.00 s (44.36 MB)AI tools. One workspace”um”/“uh” fillers, a failed “motion graphics” start, duplicate “All this in” and “Also you can” restarts, and a repeated Premiere/Final Cut phrase
talk-codex-b.mp440.00 s24.83 s26.83 s (40.80 MB)Upload. Prompt. Edit”Finally…” false start and dead air, “uh”, several multi-second pauses, and an unfinished upload explanation at the end
talk-codex-c.mp440.01 s10.50 s12.50 s (19.04 MB)Human taste meets AI”Give me a…”, a failed intro, two long silent waits (8.64 s and 5.93 s), “uh”, and an unfinished third-part intro
Folder total120.05 s63.33 s69.33 s3 matching cardsAbout 56.7 s shorter before adding titles

(These three edits are the direct output of the seven-prompt batch run, without manual post-run word editing. Full decoding and 15 sampled frames checked technical delivery; the run did not include a complete human listening review. Follow the review checklist before publishing.)

How do you batch-edit a folder of clips in Codex in five steps?

  1. Connect ChatCut Desktop once. Open Codex in the ChatGPT desktop app or codex in your terminal on macOS 13+ or Windows 10+ (x64), send Read ChatCut.io/desktop to install ChatCut, sign in to ChatCut Desktop, and start a fresh session so Codex loads ChatCut’s tools.
  2. Import and transcribe the whole folder. Start codex inside your footage directory and ask it to import every clip into one ChatCut project and run speech transcription across all of them.
  3. Cut and reframe each clip on its own timeline. Have Codex create a dedicated 9:16 timeline per clip (Short A, Short B, Short C), cut fillers, false starts, and dead air from each transcript, and verify vertical framing on off-center speakers.
  4. Apply shared packaging and selective B-Roll. Reuse one word-level caption style, one 2-second title template, and one auto-ducked music bed across every timeline, and require a credit estimate before generating any paid AI B-roll.
  5. Batch-export and verify. Render all timelines to local 1080×1920 MP4s, ask for a cut summary table, and spot-check captions, framing, and audio before publishing.

What do you need before you start?

  • macOS 13+ (Apple silicon or Intel) or Windows 10+ (x64). ChatCut Desktop runs natively on Mac and Windows; Linux, phones, and chatgpt.com in a web browser cannot install Desktop.
  • Codex CLI or the ChatGPT desktop app. Install the ChatGPT desktop app (and choose Codex) or install Codex CLI (codex) in Terminal or PowerShell. Our recorded run used high reasoning effort; it did not compare effort levels.
  • A signed-in ChatCut account. Sign in inside ChatCut Desktop so cloud transcription and stock libraries work. Free covers editing, captions, and local exports; add a paid plan ($25/month for 100 credits) only if you want ChatCut-hosted AI video or image generation.
  • A clean local folder of source clips. Put the takes you want to batch-process into one readable directory (this run used H.264 .mp4 talking-head clips) and set an explicit credit ceiling—such as 5 credits max—before requesting generated B-roll.

Why split a batch edit into A-Roll and B-Roll passes?

Separating A-Roll from B-Roll helps keep the spoken edits and overlays organized across three timelines:

  • A-Roll is the spoken spine of each Short: imported camera takes, transcript cleanup, 9:16 subject framing, and word-timed captions (Steps 2 to 4 below).
  • B-Roll is the shared packaging and visual support layered around that spine: 2-second title cards, cutaway footage, and ducked background music (Steps 5 to 7 below).

If you ask Codex to trim three transcripts, build title cards, generate B-roll, and duck music in a single prompt, a later change to Clip B’s spoken cut may require reviewing its overlays and audio timing. Review the spoken cuts before adding titles, cutaways, and music.

How do you edit a folder of videos with Codex step by step?

Steps 1 to 4 lock the A-Roll across all three clips. Steps 5 to 8 apply shared B-Roll packaging, export the finished MP4s, and verify the files.

Step 1. Connect Codex to ChatCut Desktop

On a fresh Mac or Windows setup, open a new Codex task (or run codex in your terminal) and send the one-line setup instruction from chatcut.io/desktop (also available on the Codex plugin page):

Try this prompt
Read ChatCut.io/desktop to install ChatCut

Codex follows the Desktop installation instructions and runs ChatCut’s official installer (curl -fsSL https://chatcut.io/install.sh | sh on macOS or irm https://chatcut.io/install.ps1 | iex in Windows PowerShell—no Node.js or npm required). ChatCut Desktop launches, opens browser sign-in, registers its local STDIO MCP server in ~/.codex/config.toml, and installs ChatCut’s editing skills into ~/.agents/skills. After signing in, start a new Codex session so the agent loads the newly registered tools. OpenAI’s Plugins documentation also explains starting a new session after installing bundled skills.

In our November 18 terminal session (codex-cli 0.169.0-alpha.11.1), ChatCut Desktop was already installed and connected on the test Mac, so we did not time a first-time download. Reading the Desktop guide, confirming the live desktop surface, creating a dedicated local project, and checking the account credit balance took about 1 minute and 0 ChatCut credits:

ChatCut Desktop workspace connected to Codex CLI, showing the three 40-second raw clips in the Media Pool, the 16:9 presenter in the Viewer, and tabs for Timeline, Short A, Short B, and Short C above a 2-minute combined timeline.
One local ChatCut Desktop project holds the whole batch (captured mid-run with the left account sidebar and unused built-in chat panel cropped out): the three 40-second source clips sit in Media Pool while Timeline, Short A, Short B, and Short C live side by side as separate tabs.

Step 2. Import the whole folder and transcribe every clip at once

With codex pointed at our footage folder—containing talk-codex-a.mp4 (40.04s), talk-codex-b.mp4 (40.00s), and talk-codex-c.mp4 (40.01s), all 1920×1080 at 23.976 fps—we sent our first editing prompt verbatim:

Try this prompt
Import every clip in this folder into one ChatCut project and transcribe them.

Instead of making you click through a file picker three times, Codex passed all three file paths in a single batch import, triggered word-timed cloud speech transcription on all three assets simultaneously, and placed the three 40-second clips end-to-end on a 120-second reference timeline to inspect the raw picture. Importing, transcribing all three takes, and rendering a three-clip preview sheet took about 1.3 minutes at 0 ChatCut credits.

Three 16:9 horizontal preview frames from talk-codex-a.mp4, talk-codex-b.mp4, and talk-codex-c.mp4 after batch import: the presenter speaks centered in Clip A, looks down at the desk during a silent pause in Clip B, and sits left of center while looking at notes in Clip C.
Step 2 preview across all three imported 16:9 clips (0 credits): inspecting early frames immediately reveals unedited desk-looking pauses and off-center seating in Clips B and C.

Step 3. Cut fillers, false starts, and dead air into three 9:16 timelines

Next, we asked Codex to clean up the speech and convert each clip into its own vertical Short:

Try this prompt
For each clip, remove filler words, false starts and long pauses, and make a 9:16 version.

Codex created three separate 1080×1920 (30 fps) timelines—Short A, Short B, and Short C—inside the same project, read the word-timed transcripts alongside visual pause frames from the source footage, and trimmed each take independently (about 2.5 minutes, 0 ChatCut credits):

  • Short A (40.04s → 28.00s): Removed “um” and “uh” fillers, an aborted “motion graphics” sentence start, duplicate “All this in” and “Also you can” restarts, and a repeated Premiere/Final Cut phrase.
  • Short B (40.00s → 24.83s): Cut a “Finally…” false start and its silent wait, dropped “uh”, tightened several multi-second pauses, and removed an incomplete upload line at the tail.
  • Short C (40.01s → 10.50s): Cut “Give me a…” and a failed intro, removed two long stretches of silent waiting (8.64 seconds and 5.93 seconds), dropped “uh”, and trimmed an unfinished third-part intro at the end.

The run applied 2-frame audio edge fades at cuts to reduce abrupt edges; it did not include a listening check of every splice. The presenter sat off-center in Clips B and C, so Codex adjusted horizontal framing on Short B and Short C and inspected vertical previews. We kept static vertical framing on the presenter across this batch rather than adding digital punch-in zooms; if you want scale changes or subtle whooshes on key lines, ask for them in a separate A-Roll pass after checking the base crop.

Side-by-side 9:16 vertical frames from Short A on the left and Short C on the right, showing the presenter cleanly centered in both portrait frames without clipping his glasses or face.
Step 3 vertical reframing across the batch: Short A (left) worked with a center crop, while Short C (right) needed a horizontal offset so the off-center 16:9 take stayed centered in 9:16.

Step 4. Apply one word-level caption template across all three Shorts

With the three spoken edits locked, we asked for a single AI caption design across the whole batch:

Try this prompt
Add the same caption style to all three: bold white words, the spoken word highlighted in orange.

In about 1.5 minutes (0 ChatCut credits), Codex authored one reusable custom caption template—bold white Mulish type, capped at two lines in the lower safe zone, using each word’s exact start and end timestamps so only the word currently being spoken turns orange—and bound that same component to Short A, Short B, and Short C. Before moving on, Codex rendered two sampled frames on Short A (f12 at 0.4s and f24 at 0.8s) to verify that the orange highlight stepped cleanly from “you” to “not” while earlier words returned to white. For accessible captions and why automatic transcription needs review, see the W3C WAI captions guide.

Two sampled 9:16 preview frames f12 and f24 from Short A reading 'Means you can not only' in bold white Mulish text: in f12 only 'you' is orange, and in f24 'you' returns to white while 'not' turns orange.
Frame-by-frame caption check on Short A (f12 at 0.4s vs. f24 at 0.8s): one shared caption template drives active-word orange highlighting across all three timelines at 0 credits.

Step 5. Add a shared 2-second title card to each clip

Now the B-Roll packaging pass starts. Instead of building three unrelated intros, we told Codex to summarize each Short’s main thesis inside one shared 2-second Motion Graphics title layout:

Try this prompt
Give each short a 2-second title card with its main point, using the same template.

In about 0.8 minutes (0 ChatCut credits), Codex shifted the spoken clips and captions forward by 2.0 seconds (60 frames at 30 fps) on all three timelines and placed a matching black title card from 0:00 to 0:02, pairing an orange series label (CODEX × CHATCUT / 01 through 03) with a bold white headline tailored to each clip’s transcript:

Three 9:16 opening title cards at 1.0s from Short A, Short B, and Short C side by side on black backgrounds with small orange series labels: 'CODEX × CHATCUT / 01 — AI tools. One workspace', 'CODEX × CHATCUT / 02 — Upload. Prompt. Edit', and 'CODEX × CHATCUT / 03 — Human taste meets AI'.
One 2-second title template instantiated across all three Shorts in this run (0 ChatCut credits): consistent typography and series numbering, with each headline pulled from that clip's spoken point.

Step 6. Quote and generate one AI B-Roll cutaway for Clip B

You rarely need paid AI footage on every clip in a batch. To illustrate a conceptual line in Short B without blowing our 5-credit session cap, we asked Codex to quote the exact AI video generation cost before submitting anything:

Try this prompt
Generate one B-roll clip for clip B only and place it over one line. Tell me the credit cost first.

Codex checked the preflight price for Seedance 2.5 Flash (4 seconds, 720p, 9:16) and reported an exact estimate of 2.88 ChatCut credits against our 59.22-credit balance. Because 2.88 credits sat comfortably below our 5-credit ceiling, Codex submitted the job, waited for completion without resubmitting, confirmed settlement at 2.88 credits (59.22 → 56.34), and placed the 4-second cutaway over 10.867s–14.867s of Short B (“to the first prompt. Clean up all the filler…”) while keeping the presenter’s voice and orange-highlighted captions on top (about 3.6 minutes end to end).

Two honest details about this shot: its 720×1280 source was scaled into the 1080×1920 timeline (not native 1080p generation), and the laptop screen inside the generated clip shows a generic mock timeline—never pass off AI B-roll as a real product screen recording.

2x2 contact sheet from Short B (frames f326, f386, f445, and f446): three frames show a warm-lit over-the-shoulder shot of hands typing on a laptop running generic video editing software with captions 'to the first prompt' and 'Clean up all the filler', followed by f446 cutting cleanly back to the speaker.
Step 6 on Short B (2.88 ChatCut credits): a 4-second 720p Seedance 2.5 Flash cutaway covers 10.87s–14.87s with a slow camera push while the spoken track and captions stay active, then cuts back to the speaker at f446.

Step 7. Reuse one auto-ducked background music track across the batch

Rather than paying to generate three separate music tracks, we asked Codex to lay one restrained instrumental bed underneath all three timelines and duck it under speech:

Try this prompt
Add the same light music bed to all three, ducked under the voice.

Codex searched ChatCut’s stock audio catalog, downloaded the CC0 instrumental track Daylight by Andrewkn on Freesound once into the project, and placed it on a Music track across Short A, Short B, and Short C at -6 dB base gain with a 1.0-second fade-in, a 1.5-second fade-out, and automatic ducking keyed to the Voice track (about 1.2 minutes, 0 ChatCut credits; if you want a custom-composed stem instead, ChatCut’s AI music generator charges about 0.2 credits per instrumental track).

Because a timeline screenshot only shows track blocks—and in our window capture below, the Music track sits below the vertical scroll fold—Codex also ran an audio mix readout through ChatCut’s export engine on Short C. That check confirmed -19.3 LUFS integrated loudness (-0.7 dBFS peak), with a checked voice segment around -22.3 dBFS RMS and a checked music segment as low as -46.8 dBFS during active speech. These segment measurements do not establish an average for the entire voice track.

Cropped ChatCut Desktop workspace with Short B active (00:26:25): Media Pool shows the 2:06 Daylight CC0 audio asset alongside the 0:04 generated Clip B cutaway and the three 0:40 source clips; Viewer shows the 'Upload. Prompt. Edit' title card; Timeline shows caption/title tracks C3 and C2, trimmed video segments, and the green A1 Voice waveform.
Short B selected in ChatCut Desktop after Step 7 (0 credits for stock CC0 audio): Daylight sits in Media Pool for reuse across all three timelines while Short B's title layers, trimmed video cuts, and Voice waveform remain individually editable.

Step 8. Batch-export 1080x1920 MP4s and verify every file in the terminal

Finally, we asked Codex to render all three vertical timelines to disk and return a structured edit ledger:

Try this prompt
Export all three as 1080x1920 MP4s into an output folder and give me a summary table: clip, original length, final length, what was cut.

Codex queued local Desktop exports for short-a.mp4, short-b.mp4, and short-c.mp4 as three export jobs (1080×1920, 30 fps, H.264 video, 48 kHz stereo AAC audio) and finished rendering in about 1 minute at 0 ChatCut credits. After export, Codex looped over the three output MP4s in the terminal with ffprobe and ffmpeg to confirm exact stream dimensions, zero decode errors across the full duration of every file, and five evenly spaced check frames (10%, 30%, 50%, 70%, 90%) per Short:

3x5 verification grid of 15 frames extracted at 10%, 30%, 50%, 70%, and 90% of duration from short-a.mp4 (top row), short-b.mp4 (middle row, showing the laptop B-roll cutaway at 50%), and short-c.mp4 (bottom row, showing the 'Human taste meets AI' title card at 10% and reframed speaker across 30%–90%).
All 15 terminal verification frames (10%, 30%, 50%, 70%, and 90% across Shorts A, B, and C): face crops, title cards, active-word orange captions, and Clip B's 50% cutaway all landed inside safe bounds—while also exposing exact caption words to proofread before publishing.

Here is the timing and ChatCut credit ledger for this batch project. Stage times are approximate observation windows that include preparation, adjustments, and screenshots; they are not isolated tool benchmarks. The roughly 13.5-minute wall-clock interval includes gaps between stages. Subsequent export checks and reporting are extra; Codex subscription or API costs were not measured:

StepWhat Codex did across the 3-clip batchObserved timeChatCut credits
1. Connect & create projectVerified existing Desktop connection, created project, checked billing~1.0 min0.00
2. Batch import & transcribeImported 3 local 16:9 MP4s (120.05s total) and transcribed all three~1.3 min0.00
3. Rough cut & 9:16 reframeBuilt Short A/B/C (28.0s, 24.8s, 10.5s), fixed B/C horizontal crop~2.5 min0.00
4. Shared word captionsBuilt custom white/orange Mulish template, applied to all 3, checked f12/f24~1.5 min0.00
5. Shared 2s title cardsShifted speech +2s and added matching black/orange title cards (01–03)~0.8 min0.00
6. Clip B AI cutawayQuoted 2.88 credits, generated 4s 720p Seedance 2.5 Flash shot, placed at 10.9s~3.6 min2.88
7. Shared music & duckingDownloaded CC0 track once, added -6 dB ducked music bed across all 3~1.2 min0.00
8. Batch MP4 exportRendered three 1080×1920 MP4s locally (69.33s total); later verification excluded~1.0 min0.00
Batch session totalConnection check through 3 finished local 1080×1920 MP4s~13.5 min2.88

(Which tools did Codex use? It combined ChatCut Desktop’s local editing, transcription, caption, graphics, generation, stock-media, preview, and export tools with terminal checks. See our video editing MCP servers comparison for other integrations.)

Which prompts can you copy for other Codex video editing jobs?

Run codex inside the folder holding your raw recordings so it can pass exact local paths without manual uploads, and keep one editing stage per turn.

Batch talking-head folder cleanup (0 ChatCut credits)

Try this prompt
Import every MP4 in this folder into one ChatCut Desktop project and transcribe them. Create a separate 9:16 1080x1920 timeline for each clip, cut false starts, filler words, repeated lines, and pauses over 0.6 seconds, and check rendered preview frames so off-center speakers stay centered. Stop before adding captions, music, or paid generation, and show me a table of original vs. trimmed lengths.

Long interview or podcast to multi-timeline 9:16 Shorts

If you are starting from one 30-minute episode instead of pre-split takes, see our guide to turning long videos into Shorts and use this two-step brief:

Try this prompt
Import this interview recording into ChatCut Desktop, transcribe it, and list the 4 strongest self-contained 30-to-50-second moments with exact source timestamps and the opening hook sentence for each. Wait for my selection before creating separate 9:16 timelines with bold word-level captions.

Product feature batch with a strict credit cap

Try this prompt
In one ChatCut Desktop project, import the three feature clips in ./raw-takes and build three 9:16 timelines. Trim dead air and stumbles, add one shared 2-second opening title template and bold lower-third captions, and quote the exact ChatCut credit cost before generating any B-roll—do not spend more than 5 credits total.

What do you still need to check yourself before publishing?

Automated ffprobe checks and sampled frames confirm technical properties, not editorial judgment. The recorded run did not include a full human listening review. Before publishing:

  1. Proofread captions against the voice. Play each Short with sound on and check names, technical terms, and incomplete sentences. Correct subtitle text without deleting spoken footage unless a cut is intended.
  2. Check the beginning and ending. Listen for incomplete thoughts and trim unnecessary room tone so the Short ends on a complete point.
  3. Inspect each 9:16 crop. Check the speaker’s face throughout the edit, especially when their posture changes. Ask Codex for rendered preview frames and review the result in the Viewer.
  4. Distinguish generated B-roll from screen recordings. The laptop screen in this run is synthetic, generic UI. Use real recordings for an actual product demonstration and follow YouTube’s synthetic content disclosure policy where applicable.
  5. Listen across splices and ducked music. The recorded mix analysis supports ducking on Short C; its integrated loudness alone does not prove it. Listen to all three Shorts to judge speech clarity, breaths, and music levels.

How do you troubleshoot Codex and ChatCut Desktop?

ChatCut tools do not appear in Codex after installation

Codex loads MCP servers and bundled skills when a session starts (OpenAI Plugins docs). If you just ran Read ChatCut.io/desktop to install ChatCut, exit and reopen codex in your terminal (a cleared screen alone does not reload MCP servers) or open a brand-new chat in the ChatGPT desktop app. If tools are still missing, check two things: confirm you completed sign-in inside the ChatCut Desktop window, and run codex mcp list (or type /mcp inside Codex CLI) to verify the local server is registered in ~/.codex/config.toml. Do not use the Codex IDE extension to browse plugins—OpenAI’s plugin directory runs in the ChatGPT desktop app and Codex CLI, though standalone local MCP servers configured in config.toml are shared.

A paid B-roll generation takes a couple of minutes

In this recorded run, the B-roll stage took about 3.6 minutes including generation, checking, and placement. If Codex stops waiting before a job finishes, ask it to check that existing job; requesting a new generation can create another charge. Ask Codex to check the status of the existing job and place that asset once settled. Verify any completed deduction under Avatar menu → Credits history → Detail in ChatCut Desktop (Credits policy).

Codex created and edited a project, but no ChatCut window popped up

By design, creating or targeting a local .chatcutproject from an external agent leaves its window closed so batch work does not steal focus (Edit a Desktop Project from Your Agent). Launch ChatCut Desktop anytime and open the project from Projects (or ask Codex to open the project window) to play and fine-tune the timelines visually.

You want to finish color or audio in Premiere Pro or DaVinci Resolve

Alongside local video export (up to 4K, plus HDR on macOS), ChatCut Desktop exports FCP7 XML (XMEML) for Adobe Premiere Pro and DaVinci Resolve, plus editable CapCut or Jianying drafts when installed locally (Product Facts). Final Cut Pro FCPXML is not supported, and captions, transitions, and unrendered motion graphics do not carry over in XML—render transparent ProRes 4444 motion-graphics overlays (paid plans) if you need them in an external NLE.

Using a different agent? The same ChatCut edit works from ChatGPT, Claude Code, Cursor, Antigravity, Grok Bot, OpenClaw, Hermes Agent, Meta Muse and WorkBuddy; each guide covers that agent’s install and quirks.

Three ways to try ChatCut
Edit local files on your computer For long footage, screen recordings and 4K exports. macOS and Windows. Download DesktopDownload for macOSDownload for WindowsOpen in your browser
On a computer, download ChatCut Desktop.
Start in your browser Free plan, nothing to install. The editor opens with this prompt: Remove filler words, false starts, and long pauses from my clips, make 9:16 versions, and add bold word-level captions. Try this prompt
Already using an AI agent? Send this one message to the agent you use.
Read ChatCut.io/desktop to install ChatCut
Send it in a new Codex task. Setup guide

Questions about editing video with Codex

Can Codex edit videos?
Yes, when connected to a video editor on macOS 13+ or Windows 10+ (x64). Codex can run editing code and connected tools; a ChatCut project provides the editable video timeline used in this walkthrough. Connecting ChatCut Desktop gives Codex local tools to import footage, cut from transcripts, add editable captions, titles, B-roll, and music across multiple timelines, and export MP4 or XML files.
How is editing video in Codex different from using ChatGPT?
Single-video edits work much the same in both, since ChatGPT and Codex share one plugin ecosystem on desktop. Codex shines when you run it in a local folder or Codex CLI to batch-process multiple files at once—importing an entire directory, reusing one custom caption and title template across separate timelines, and verifying exported MP4s from the terminal with ffprobe and ffmpeg.
Does Codex video editing work on Linux, the web, or mobile?
ChatCut Desktop runs on macOS 13 or newer (Apple silicon or Intel) and Windows 10 or newer (x64); Linux is not supported, and Desktop cannot be installed from chatgpt.com in a browser or on a phone. If you need to continue an existing cloud project in ChatCut Web from the desktop app, use ChatCut's hosted Web plugin instead.
How much does it cost to batch-edit videos with Codex and ChatCut?
Two separate meters apply. Codex's reasoning uses its own subscription allowance or API billing; access depends on your account and surface. On the ChatCut side, local imports, speech transcription, timeline cuts, captions, agent-authored title cards, stock CC0 music, and local Desktop MP4 exports cost 0 ChatCut credits and carry no watermark. You spend ChatCut credits only on ChatCut-hosted AI media generation—in our three-video batch test, one 4-second Seedance 2.5 Flash cutaway cost 2.88 credits total (paid plan required for AI video and image generation, starting at $25/month for 100 credits).
Which Codex plugins are useful alongside a video editor?
Choose additional tools for a specific job, and check current access and billing before installing. The official Remotion and HyperFrames repositories linked above document code-driven video workflows; this recorded run did not test those integrations.
Can I adjust the cuts, framing, and captions by hand after Codex finishes?
Yes. Every clip, trim, caption track, Motion Graphic title card, B-roll layer, and music track sits inside a standard local .chatcutproject in ChatCut Desktop. In our batch run, Short A, Short B, and Short C each had their own timeline tab inside one project so we could scrub frames, fix misheard caption words, or nudge horizontal framing without re-running prompts.
How do I install ChatCut in Codex CLI or the ChatGPT desktop app?
Open a new task in Codex (inside the ChatGPT desktop app or by running codex in Terminal or PowerShell on macOS 13+ or Windows 10+ x64) and send 'Read ChatCut.io/desktop to install ChatCut'. Allow the official installer command, complete sign-in inside ChatCut Desktop, and start a new Codex session so the local MCP tools and editing skills load.

Checking your footage...

Less editing. More creating.

Download ChatCut Desktop free and make your first video today.

Download Desktop Download for macOS Download for Windows Try it for free